MODEL-BASED OBJECT POSE IN 25 LINES OF CODE

In this paper, we describe a method for finding the pose of an object from a single image. We assume that we can detect and match in the ima ge four or more noncoplanar feature points of the object, and that we know their relative geometry on the object. The method combines two al gorithms; the first algorithm, POS (Pose from Orthography and Scaling) approximates the perspective projection with a scaled orthographic pr ojection and finds the rotation matrix and the translation vector of t he object by solving a linear system; the second algorithm, POSIT (POS with ITerations), uses in its iteration loop the approximate pose fou nd by POS in order to compute better scaled orthographic projections o f the feature points, then applies POS to these projections instead of the original image projections. POSIT converges to accurate pose meas urements in a few iterations. POSIT can be used with many feature poin ts at once for added insensitivity to measurement errors and image noi se. Compared to classic approaches making use of Newton's method, POSI T does not require starting from an initial guess, and computes the po se using an order of magnitude fewer floating point operations; it may therefore be a useful alternative for real-time operation. When speed is not an issue, POSIT can be written in 25 lines or less in Mathemat ica; the code is provided in an Appendix.